Data Scientist - I

Khatabook; Bengaluru; On-site; INR 1,000,000 - 1,500,000; Full time

Job summary

Khatabook is looking for a highly skilled Data Scientist - I to join their credit risk modelling team. This role contributes to developing and refining credit and collections risk models, leveraging SMS and other datasets, while utilizing machine learning and deep learning techniques.

The ideal candidate will have a strong background in Data Science, with proficiency in Python and experience in model deployment. Join us to help empower MSMEs throughout India and innovate in the financial space.

Qualifications

• 1+ years of Data Science/Machine Learning experience.
• Strong knowledge in statistics and tree-based techniques.
• Strong inclination towards data insights generation.

Responsibilities

• Monitor, evaluate, and refine model performance over time.
• Design, develop, and deploy end-to-end data science solutions.
• Collaborate with cross-functional teams for data-driven impact.

Skills

Data Science

Machine Learning

Deep Learning

Python Programming

Statistics

SQL

Education

Bachelor's or Master's in Engineering or equivalent

Tools

pandas

scikit-learn

SQL

TensorFlow

PyTorch

Job description

Overview

Are you passionate about solving roadblocks & challenges faced by MSMEs in India? MSMEs contribute significantly to India’s total GDP. 90% of India’s ~$1 Trillion Retail Market is controlled by Micro, Small & Medium Enterprises (MSMEs), amounting to ~$900B worth of commerce flows through these ~60M MSMEs in the form of shops/kiosks/homes, scattered all over the country. We at Khatabook have a vision to empower MSMEs and help them increase their incomes. We have built a product that brings efficiency in MSME operations by providing them easy to use tools to manage their receivables, inventory and billing which creates transparency in their cash flow. Within the Khatabook platform, we have also enabled the facility to take loans for their short term working capital needs for select Khatabook users that are displaying good credit behaviour. Our app has been downloaded over 100 Million times with a monthly active user base of 8 Million+ which are adding 220 Million+ transactions with a transaction value of $18 Billion.

Why work with us?

People are our biggest asset! At Khatabook, every one of us is a dynamic superstar. We’ve carefully bred an ecosystem that hires nothing but incredibly and exceptionally talented people who can dream, collaborate, experiment, and break new ground. We’re a strong team that looks out for each other.

Your role: Data Scientist - I

We are seeking a highly skilled and innovative Data Scientist - I to strengthen our credit risk modelling team. You will play a pivotal role in monitoring, developing and advancing our suite of credit and collections risk models, with a particular focus on harnessing the power of SMS and other alternative datasets. If you are passionate about machine learning, deep learning, and applying large language models (LLMs) to real-world financial challenges, we want to connect with you.

What would you do at Khatabook?

• Monitor, evaluate, and refine model performance over time, ensuring reliability and alignment with business goals.
• Design, develop, and deploy end-to-end data science solutions that address complex business problems across lending, insurance, investments, and payments.
• Collaborate with cross-functional teams including product, engineering, and business to identify opportunities for data-driven impact.
• Continuously explore and implement state-of-the-art techniques in machine learning, deep learning, NLP and Generative AI.
• Drive experimentation and rapid prototyping to validate hypotheses and scale successful models to production.

What are we looking for?

• Bachelor's or Master's in Engineering or equivalent.
• 1+ years of Data Science/Machine Learning experience.
• Strong knowledge in statistics, tree-based techniques (e.g., Random Forests, XGBoost), machine learning (e.g., MLP, SVM), inference, hypothesis testing, simulations, and optimizations.
• Strong inclination towards figuring out complex patterns in data, insights generation, root cause analysis, automating them through Dashboards.
• Strong Python programming skills and basic experience in building Data Pipelines in Python, Airflow along with feature engineering.
• Proficiency in pandas, scikit-learn, SQL and familiarity with TensorFlow/PyTorch.
• Bonus: Experience with deep learning techniques, understanding of DevOps/MLOps, including creating Docker containers and deploying to production.